© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1010
    Prev
    Next
    INDEX
    Explanations

    scientific terms and variables associated with measurements and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or commands, often with percentages

    np_acts-logits-general · gemini-2.0-flash

    numbers and specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.85
    ↵↵
    -0.84
     a
    -0.81
     the
    -0.79
    ↵
    -0.79
    <eos>
    -0.79
     I
    -0.77
     (
    -0.75
     A
    -0.72
     $\
    -0.70
    POSITIVE LOGITS
     متعلقه
    1.55
    rungsseite
    1.44
     تانيه
    1.39
     ویکی‌آمباردا
    1.39
    ChildScrollView
    1.36
     للاسماء
    1.34
     CreateTagHelper
    1.33
    expandindo
    1.29
     فريبيس
    1.29
    endphp
    1.27
    Activations Density 0.654%

    No Known Activations